{"id":4523,"date":"2025-03-22T14:16:02","date_gmt":"2025-03-22T22:16:02","guid":{"rendered":"https:\/\/www.xorph.com\/nfd\/?p=4523"},"modified":"2025-03-22T14:33:32","modified_gmt":"2025-03-22T22:33:32","slug":"ahiru-no-omocha","status":"publish","type":"post","link":"https:\/\/www.xorph.com\/nfd\/2025\/03\/22\/ahiru-no-omocha\/","title":{"rendered":"Ahiru no omocha"},"content":{"rendered":"<p><iframe src=\"https:\/\/friend.camp\/@aparrish\/113997725623507924\/embed\" class=\"mastodon-embed\" style=\"max-width: 100%; border: 0\" width=\"400\" allowfullscreen=\"allowfullscreen\"><\/iframe><script src=\"https:\/\/friend.camp\/embed.js\" async=\"async\"><\/script><\/p>\n<p>While I&#8217;ve never managed to finish my long-incubated and sprawling essay about large language models and Alfred Jarry, I think that if you know me, you already know my attitude toward the proponents of the former. Nevertheless, at the request of my employer, I have tried out a couple ways of using them in my work. I tested out cloud-driven code-completion interfaces long enough to learn that they hinder me more than they help, and anyway I don&#8217;t like constantly feeding our clients&#8217; intellectual property back into someone else&#8217;s text corpus. And even if those things weren&#8217;t true, my concerns about the intake and exhaust of the server farms involved would have been enough to make the experience undesirable.<\/p>\n<p>I have also tried running some open-weight models directly on my laptop, where I know my data will remain, and where I can observe that the power draw involved is not vaporizing any rivers. The results are slow and of middling quality, but good enough for things like &#8220;just tell me what fucking regex I need.&#8221; (I do still google things first, but at this point, I&#8217;m not sure using their search service is any more virtuous than using an LLM.)<\/p>\n<p>It wasn&#8217;t so long ago that the people promulgating the ascendance of statistical models were attached to the term &#8220;machine learning.&#8221; Machines cannot learn, but humans can, even me. One of the things I am learning, along with Kat, is Japanese. I&#8217;ve made use of textbooks, mnemonics, evening classes, and apps to this end, and I&#8217;ve made a lot of progress, which is to say I&#8217;m about 1% of the way to being able to converse with a preschooler. Japanese is hard.<\/p>\n<p>Textbooks are challenging to use without an instructor, and while I appreciated working with such an instructor for a remote course through our local cultural center, the video-call medium is pretty painful in a class setting. Apps are nice for building a habit and refreshing myself, but as I&#8217;m sure you know, they more or less all run on a model of drilling by way of quizzes. Like many people who were praised for youthful conformance to school standards, I retain the test-taking skills that were hammered into me at a formative age. That means my brain is tuned for using process of elimination and context clues to answer quizzes <em>without<\/em> learning anything new, which is a whole other essay I will never finish, but anyway this is why the apps yield only grudging progress.<\/p>\n<p>I know enough about my own capabilities, and about general educational theory, to understand that if I want to learn something in a persistent way then the most valuable exercise is trying to explain it to someone else. When software nerds do this to solve a problem, we call it <a href=\"https:\/\/en.wikipedia.org\/wiki\/Rubber_duck_debugging\" title=\"I'm not sure that duck is actually in use, photo caption.\">rubber-ducking<\/a>. I don&#8217;t actually own a rubber duck. But I do have a laptop with an LLM runtime on it. You can see how I got here.<\/p>\n<p>&#8220;The thing is there&#8217;s so much basic vocabulary to learn,&#8221; I told Kat, &#8220;and a lot of it is English loan words, but then a lot more isn&#8217;t. And so many of the words sound alike but mean such different things. So I thought, hey, I can just tell the computer to have a conversation with me, and I&#8217;ll <em>have<\/em> to explain the differences between the words and what they mean, and even use them in sentences. It&#8217;s a proven technique. I think it might actually help!&#8221;<\/p>\n<p>Kat, who I believe I mentioned is also learning Japanese, gave me a steady look and replied: &#8220;or you could just tell those things to me.&#8221;<\/p>\n<p>Sometimes the problem I solve by explaining myself aloud isn&#8217;t even the one I knew about.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>While I&#8217;ve never managed to finish my long-incubated and sprawling essay about large language models and Alfred Jarry, I think that if you know me, you already know my attitude toward the proponents of the former. Nevertheless, at the request of my employer, I have tried out a couple ways of using them in my [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[141,19,77,34],"tags":[],"class_list":["post-4523","post","type-post","status-publish","format-standard","hentry","category-kat","category-mild-lunacy","category-shame","category-travel-and-acronyms"],"_links":{"self":[{"href":"https:\/\/www.xorph.com\/nfd\/wp-json\/wp\/v2\/posts\/4523","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.xorph.com\/nfd\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.xorph.com\/nfd\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.xorph.com\/nfd\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.xorph.com\/nfd\/wp-json\/wp\/v2\/comments?post=4523"}],"version-history":[{"count":14,"href":"https:\/\/www.xorph.com\/nfd\/wp-json\/wp\/v2\/posts\/4523\/revisions"}],"predecessor-version":[{"id":4538,"href":"https:\/\/www.xorph.com\/nfd\/wp-json\/wp\/v2\/posts\/4523\/revisions\/4538"}],"wp:attachment":[{"href":"https:\/\/www.xorph.com\/nfd\/wp-json\/wp\/v2\/media?parent=4523"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.xorph.com\/nfd\/wp-json\/wp\/v2\/categories?post=4523"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.xorph.com\/nfd\/wp-json\/wp\/v2\/tags?post=4523"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}